© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39450
    Prev
    Next
    INDEX
    Explanations

    philosophical and multilingual concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    仍然
    -1.38
     still
    -1.31
    ποίη
    -1.30
    Still
    -1.23
    ে
    -1.20
    铿
    -1.20
    仍
    -1.19
    ון
    -1.18
     possible
    -1.18
    疍
    -1.17
    POSITIVE LOGITS
    ÇÕES
    1.37
    了他
    1.32
     his
    1.28
     איך
    1.27
    IONES
    1.27
    tava
    1.25
     andar
    1.24
     organes
    1.24
    ELESS
    1.23
    醅
    1.23
    Activations Density 0.012%

    No Known Activations